Evaluate gene sets identified by SDAN

Setup

Load R libraries

library(data.table)
library(ggplot2)
library(ggpubr)
library(tidyr)
library(limma)
library(biomaRt)
library(fgsea)
library(goseq)

theme_set(theme_classic())

cell_type_name = params$cell_type_name
graph_weight = params$graph_weight

cell_type_name

## [1] "cd4"

graph_weight

## [1] "10.0"

Check enrichment of gene sets

Read in gene info and gene set assignments

file_tag = sprintf("%s_BL_%s", cell_type_name, graph_weight)

assayed_genes = scan(sprintf("output/gene_list_%s.txt", file_tag), 
                     what = character(), sep="\n")

gene_sets = scan(sprintf("output/name_s_%s.txt", file_tag), 
                 what = character(), sep="\n")

gene_sets = sapply(gene_sets, strsplit, USE.NAMES=FALSE, split=",")
n_genes   = sapply(gene_sets, length)
names(n_genes) = NULL
summary(n_genes)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00   25.00   27.00   26.18   28.00   29.00

length(n_genes)

## [1] 40

sort(n_genes)

##  [1]  1 23 24 24 24 25 25 25 25 25 25 26 26 26 26 26 27 27 27 27 27 27 27 28 28
## [26] 28 28 28 28 28 28 28 28 28 29 29 29 29 29 29

Find gene symbols

Find gene symbols from bioMart.

All the gene symbols that can be found in bioMart are consistent with what we have. So no need to run it.

ensembl = useMart("ensembl", dataset = "hsapiens_gene_ensembl")

gene_BM = getBM(attributes = c("hgnc_symbol", "external_gene_name"), 
                filters = "external_gene_name", 
                values = assayed_genes, 
                mart = ensembl)
length(assayed_genes)
dim(gene_BM)
gene_BM[1:2,]

table(assayed_genes %in% gene_BM$external_gene_name)

t1 = table(gene_BM$external_gene_name)
dup = names(t1)[t1 > 1]
gene_BM[gene_BM$external_gene_name %in% dup,]

table(gene_BM$hgnc_symbol == gene_BM$external_gene_name)
w2kp = which(gene_BM$hgnc_symbol != gene_BM$external_gene_name)
gene_BM[w2kp,]

Find gene symbols using the alias2Symbol function from limma.

a2s = rep(NA, length(assayed_genes))
for(i in 1:length(assayed_genes)){
  gi = assayed_genes[i]
  ai = alias2Symbol(gi)
  if(length(ai) > 1){
    print(gi)
    print(ai)
  }
  a2s[i] = ai[1]
}

## [1] "HIST1H2BC"
## [1] "H2BC5" "H2BC4"
## [1] "MPP6"
## [1] "MPHOSPH6" "PALS2"   
## [1] "MARS"
## [1] "MARS1" "SLA2" 
## [1] "SEPT2"
## [1] "SEPTIN6" "SEPTIN2"

table(is.na(a2s))

## 
## FALSE  TRUE 
##  1951    49

table(a2s == assayed_genes, useNA = 'ifany')

## 
## FALSE  TRUE  <NA> 
##    45  1906    49

gene_info = data.table(sym_in_data = assayed_genes, sym_limma = a2s)

gene_info[sym_in_data != sym_limma,]

##      sym_in_data   sym_limma
##  1:      ADPRHL2       ADPRS
##  2:          AES        TLE5
##  3:     C12orf45    NOPCHAP1
##  4:      C3orf58      DIPK2A
##  5:      C6orf99   LINC02901
##  6:        CBWD2       ZNG1B
##  7:      CXorf57        RADX
##  8:      FAM102A       EEIG1
##  9:      FAM122C      PABIR3
## 10:      FAM153C    FAM153CP
## 11:     FAM160A2      FHIP1B
## 12:        GRASP     TAMALIN
## 13:        H2AFX        H2AX
## 14:    HIST1H2AG      H2AC11
## 15:    HIST1H2BC       H2BC5
## 16:    HIST1H2BK      H2BC12
## 17:    HIST1H2BN      H2BC15
## 18:     HIST1H3A        H3C1
## 19:     HIST1H3H       H3C10
## 20:     HIST1H4C        H4C3
## 21:    HIST2H2BF      H2BC18
## 22:         LRMP       IRAG2
## 23:      MFSD14C    MFSD14CP
## 24:         MKL1       MRTFA
## 25:         MPP6    MPHOSPH6
## 26:  RNASEH1-AS1  RNASEH1-DT
## 27:        SEPT6     SEPTIN6
## 28:        SEPT9     SEPTIN9
## 29: TMEM161B-AS1 TMEM161B-DT
## 30:        ARNTL       BMAL1
## 31:     C6orf106       ILRUN
## 32:     C6orf203      MTRES1
## 33:      FAM129A      NIBAN1
## 34:     FAM160B1      FHIP2A
## 35:      FAM192A    PSME3IP1
## 36:        HEXDC        HEXD
## 37:     HIST1H1E        H1-4
## 38:     KIAA0100       BLTP2
## 39:     KIAA1551       RESF1
## 40:         LARS       LARS1
## 41:         MARS       MARS1
## 42:      PLA2G16      PLAAT3
## 43:        SEPT2     SEPTIN6
## 44:       SMIM37        MTLN
## 45:         YARS       YARS1
##      sym_in_data   sym_limma

gene_info[, gene_symbol := sym_in_data]
gene_info[which(sym_in_data != sym_limma), gene_symbol := sym_limma]

dim(gene_info)

## [1] 2000    3

gene_info[1:5,]

##    sym_in_data sym_limma gene_symbol
## 1:       ABCD3     ABCD3       ABCD3
## 2:       ABCG1     ABCG1       ABCG1
## 3:       ABHD5     ABHD5       ABHD5
## 4:        ABI1      ABI1        ABI1
## 5:      ABLIM1    ABLIM1      ABLIM1

t1 = table(gene_info$gene_symbol)
table(t1)

## t1
##    1    2 
## 1998    1

gene_info[gene_symbol %in% names(t1)[t1 == 2],]

##    sym_in_data sym_limma gene_symbol
## 1:       SEPT6   SEPTIN6     SEPTIN6
## 2:       SEPT2   SEPTIN6     SEPTIN6

gene_info[sym_in_data == "HIST1H2BC", gene_symbol:="H2BC4"]
gene_info[sym_in_data == "SEPT6", gene_symbol:="SEPTIN6"]
gene_info[sym_in_data == "SEPT2", gene_symbol:="SEPTIN2"]

Prepare gene set information

Gene set annotations (by gene symbols) were downloaded from MSigDB website.

gmtfile = list()
gmtfile[["reactome"]] = "../Annotation/c2.cp.reactome.v2023.2.Hs.symbols.gmt"
gmtfile[["go_bp"]]    = "../Annotation/c5.go.bp.v2023.2.Hs.symbols.gmt"
gmtfile[["immune"]]   = "../Annotation/c7.all.v2023.2.Hs.symbols.gmt"

pathways = list()
for(k1 in names(gmtfile)){
  pathways[[k1]] = gmtPathways(gmtfile[[k1]])
}

names(pathways)

## [1] "reactome" "go_bp"    "immune"

sapply(pathways, length)

## reactome    go_bp   immune 
##     1692     7647     5219

Filter gene sets for size between 10 and 500.

lapply(pathways, function(v){
  quantile(sapply(v, length), probs = seq(0, 1, 0.1), na.rm = TRUE)
})

## $reactome
##     0%    10%    20%    30%    40%    50%    60%    70%    80%    90%   100% 
##    5.0    7.0    9.0   12.0   17.0   23.0   31.0   44.0   71.8  120.9 1463.0 
## 
## $go_bp
##     0%    10%    20%    30%    40%    50%    60%    70%    80%    90%   100% 
##    5.0    6.0    8.0   10.0   14.0   19.0   29.0   46.0   80.8  183.0 1966.0 
## 
## $immune
##   0%  10%  20%  30%  40%  50%  60%  70%  80%  90% 100% 
##    5  162  193  197  199  199  200  200  200  200 1992

for(k1 in names(pathways)){
  p1 = pathways[[k1]]
  pathways[[k1]] = p1[sapply(p1, length) %in% 10:500]
}

Conduct enrichment analysis

dim(gene_info)

## [1] 2000    3

max_n2kp = 10

goseq_res = NULL

for(k in 1:length(gene_sets)){
  if(length(gene_sets[[k]]) < 10) { next }
  
  print(k)
  set_k = paste0("set_", k)
  print(gene_sets[[k]])
  
  genes = gene_info$sym_in_data %in% gene_sets[[k]]
  names(genes) = gene_info$gene_symbol
  table(genes)
  
  pwf = nullp(genes, "hg38", "geneSymbol")

  for(k1 in names(pathways)){
    p1 = pathways[[k1]]
    res1 = goseq(pwf, "hg38", "geneSymbol", 
                 gene2cat=goseq:::reversemapping(p1))
    res1$FDR  = p.adjust(res1$over_represented_pvalue, method="BH")
    
    nD = sum(res1$FDR < 0.1)
    
    if(nD > 0){
      res1 = res1[order(res1$FDR),][1:min(nD, max_n2kp),]
      res1$category = gsub("REACTOME_|GOBP_", "", res1$category)
      res1$category = gsub("_", " ", res1$category)
      res1$category = tolower(res1$category)
      res1$category = substr(res1$category, start=1, stop=81)
      goseq_res[[set_k]][[k1]] = res1
    }
  }
}

## [1] 1
##  [1] "CCNH"     "ERCC5"    "LAX1"     "POU2F2"   "SENP7"    "UTP6"    
##  [7] "ARHGAP10" "ARID5B"   "DTX3L"    "GBP1"     "GBP3"     "GBP5"    
## [13] "GON4L"    "IRF1"     "IRF9"     "MIER1"    "MYO1F"    "MYO1G"   
## [19] "PARP14"   "PARP9"    "RHOH"     "RNF19A"   "SAMD9L"   "SH3BP2"  
## [25] "TGS1"     "XAF1"

## [1] 2
##  [1] "CHD2"        "ADGRE5"      "ADGRG1"      "AKNA"        "CARD16"     
##  [6] "CCL4"        "CD300A"      "CTSW"        "FCRL6"       "FGFBP2"     
## [11] "GPR65"       "KIAA0040"    "MESD"        "MIR4435-2HG" "MYBL1"      
## [16] "NAA38"       "PAXX"        "RASAL3"      "S100A12"     "S1PR5"      
## [21] "SLFN12L"     "TRANK1"      "TRAV29DV5"   "TRBV6-1"     "TSPAN32"    
## [26] "TTC38"       "UBALD2"      "ZNF683"

## [1] 3
##  [1] "ABHD5"      "AL118516.1" "ATG13"      "C16orf74"   "CFAP36"    
##  [6] "CTSF"       "EVI2B"      "FAM118A"    "FAM153C"    "MAP3K8"    
## [11] "MAST4"      "NUAK2"      "PARP8"      "PNPLA2"     "RGS1"      
## [16] "RIC1"       "SCML4"      "SLC26A11"   "SLC7A6"     "SNRK"      
## [21] "TBCC"       "TCP11L2"    "TMEM107"    "ZFAND5"     "ZMAT1"     
## [26] "SCAMP4"     "SDF2"       "SP140"

## [1] 4
##  [1] "ADPRHL2"  "ASAH1"    "DHRS3"    "FAM227B"  "GPA33"    "GPX4"    
##  [7] "HINT1"    "HINT3"    "HVCN1"    "LTA4H"    "MID1IP1"  "OTUD5"   
## [13] "PHC1"     "PPIL3"    "PTGER4"   "RNF220"   "RPL41"    "SFMBT1"  
## [19] "TAGLN2"   "TRAV13-2" "TRAV9-2"  "C12orf75" "FKBP2"    "GSR"     
## [25] "HEXDC"    "LAP3"     "TIMP1"    "TMEM62"

## [1] 5
##  [1] "AC007952.4"  "AC015982.1"  "AC025164.1"  "AC087239.1"  "AC093323.1" 
##  [6] "AC245014.3"  "ADA2"        "AL133415.1"  "AL138963.3"  "ARL4A"      
## [11] "COQ10A"      "COQ8A"       "FAM122C"     "IL23A"       "ILF3-DT"    
## [16] "LETM2"       "LRRC8C-DT"   "MBNL2"       "MLXIP"       "NBPF14"     
## [21] "PLCL1"       "PRR7"        "RABL2B"      "RNASEK"      "SNHG8"      
## [26] "TBC1D7"      "TRAV38-2DV8" "TSPOAP1-AS1" "PPP2R3C"

## [1] 6
##  [1] "AC087623.3" "ATG9B"      "CD40LG"     "COQ10B"     "COQ7"      
##  [6] "CSKMT"      "MAML2"      "ODC1"       "PDE7A"      "RAB33B"    
## [11] "SLC22A17"   "SLC2A3"     "SNHG12"     "TAGAP"      "TBCCD1"    
## [16] "THAP6"      "TRAV12-1"   "TRAV41"     "UBL3"       "WHAMM"     
## [21] "WSB1"       "XIST"       "ZC3H12D"    "ZNF10"      "ZNF831"    
## [26] "CCDC43"     "PPRC1"      "ZNF267"

## [1] 7
##  [1] "CBR3"     "CHMP4A"   "CST3"     "DNAAF2"   "GGT7"     "SLC25A32"
##  [7] "TBPL1"    "USP3"     "B3GALT4"  "CCDC112"  "CTSC"     "DOCK11"  
## [13] "EFHD2"    "FKBP11"   "GNG2"     "GZMB"     "LPCAT4"   "LRRFIP1" 
## [19] "MATK"     "NKG7"     "PMVK"     "PREX1"    "PTGDR"    "SACS"    
## [25] "SH3BGRL3" "SMAP1"    "SRGN"

## [1] 8
##  [1] "AMD1"      "ARHGAP9"   "C3orf58"   "CCDC141"   "CDC42SE2"  "CHMP1B"   
##  [7] "FAM117B"   "GRASP"     "IER5"      "IFRD1"     "LBH"       "MBD6"     
## [13] "MTERF4"    "MTRNR2L12" "MYNN"      "RGCC"      "TMC8"      "TSC22D2"  
## [19] "TSC22D3"   "TTC31"     "ADAM19"    "CD69"      "GCN1"      "HIVEP3"   
## [25] "MORC3"     "STAT4"     "TCF25"     "ZEB2"

## [1] 9
##  [1] "CBLL1"    "CD38"     "CDC37L1"  "DSE"      "FCGR3A"   "GIMAP8"  
##  [7] "LCP2"     "SLC25A33" "SNX18"    "TRBC2"    "ZBTB25"   "C4orf48" 
## [13] "FAM129A"  "GNG5"     "GNPTAB"   "HLA-DPA1" "LAG3"     "NDUFA3"  
## [19] "NRROS"    "NUS1"     "OAS2"     "SLA"      "SPOCK2"   "SRP54"   
## [25] "TRAT1"    "UBR2"

## [1] 10
##  [1] "ARMCX5"   "C17orf49" "CXorf57"  "DBP"      "FOXO1"    "HIST1H3H"
##  [7] "NEK1"     "PEX6"     "PHYH"     "RNF113A"  "SBF2"     "YPEL2"   
## [13] "ZSCAN18"  "COLGALT1" "FNDC3B"   "GCA"      "GNPAT"    "KHNYN"   
## [19] "KIF21A"   "KIF21B"   "PEX26"    "PHF23"    "PLEKHA2"  "RAPGEF1" 
## [25] "TNFRSF18"

## [1] 11
##  [1] "ANAPC4"  "ATF4"    "EGR1"    "EIF1"    "EIF5"    "EPHB6"   "EPHX2"  
##  [8] "FOSB"    "JUNB"    "LYRM7"   "MALAT1"  "NDE1"    "NEU1"    "NUP54"  
## [15] "PLCD1"   "PNRC1"   "SAT1"    "SP3"     "STK19"   "TCF7"    "TOB2"   
## [22] "BHLHE40" "GPHN"    "MAF"     "SRFBP1"  "TRAC"

## [1] 12
##  [1] "AP002360.1" "ARHGAP15"   "C1GALT1"    "CD27"       "ERAP2"     
##  [6] "FCN1"       "GIMAP1"     "IGLV1-44"   "IGLV2-14"   "JPX"       
## [11] "KCNK6"      "KLF7"       "LEPROT"     "LRMP"       "PCMTD2"    
## [16] "PYROXD1"    "RAB37"      "SLC38A1"    "STK17A"     "TRBC1"     
## [21] "TTC39C"     "UCP2"       "XRRA1"      "ZNF84"      "ZNF862"    
## [26] "GZMA"       "IFI44"      "KLRG1"

## [1] 13
##  [1] "ADD3"    "C1orf43" "CASP4"   "CD48"    "CD96"    "EVL"     "FOXN3"  
##  [8] "IL16"    "IL27RA"  "LETMD1"  "SEPT6"   "SFI1"    "SH2D1A"  "SLC12A7"
## [15] "STMN3"   "TMEM204" "TRAM1"   "TTC3"    "ACAP3"   "AZI2"    "CLSTN1" 
## [22] "JAKMIP1" "N4BP1"   "SERTAD3" "UBA7"

## [1] 14
##  [1] "AKAP7"    "BDH1"     "CCR6"     "CHMP7"    "LCLAT1"   "PDE3B"   
##  [7] "PPP1R15B" "RNF139"   "SIMC1"    "TMEM63A"  "ALG11"    "ATP8B2"  
## [13] "BST2"     "GGCX"     "IFNGR2"   "LPCAT3"   "LPGAT1"   "NPDC1"   
## [19] "PIEZO1"   "RAB8B"    "TCIRG1"   "TSPAN2"   "ZDHHC20"

## [1] 15
##  [1] "ATAD1"     "GZMK"      "HDHD2"     "IGKV3-20"  "LRRC8D"    "PECR"     
##  [7] "SLC25A25"  "TOX"       "TRAV12-2"  "TRAV14DV4" "TRAV23DV6" "TRAV8-2"  
## [13] "TRBV6-6"   "ARHGEF3"   "BUD23"     "CFD"       "CX3CR1"    "LINC01871"
## [19] "NNT-AS1"   "PCED1B"    "PLP2"      "PTGER2"    "S100A11"   "TM2D1"    
## [25] "TMEM156"   "TRBV12-3"  "TTC16"     "USP30-AS1"

## [1] 16
##  [1] "AGO3"     "CDC25B"   "CDK13"    "DCTN4"    "DENND4A"  "DUSP2"   
##  [7] "FAM110A"  "FAM160A2" "FAM53C"   "GCH1"     "MAP2K5"   "MAP2K6"  
## [13] "MAP3K2"   "NOG"      "NT5C2"    "PPM1B"    "RAP2C"    "TMEM263" 
## [19] "ZNF638"   "DICER1"   "GIGYF2"   "KIF13B"   "MAP4"     "MAST3"   
## [25] "RNF144A"  "TMEM33"

## [1] 17
##  [1] "AC013264.1"   "AC025159.1"   "AC119396.1"   "AC245297.3"   "AK5"         
##  [6] "ANXA2R"       "BOLA2-SMG1P6" "C12orf29"     "DELE1"        "GIMAP6"      
## [11] "LINC00861"    "LST1"         "LYRM9"        "MCUB"         "OTULINL"     
## [16] "POLD4"        "SLC25A38"     "SNHG7"        "SPART"        "TC2N"        
## [21] "TMEM161B-AS1" "TRAV8-3"      "TRBV28"       "WAPL"         "WASHC4"      
## [26] "ZNF749"       "C1orf162"     "TUT4"

## [1] 18
##  [1] "C1orf174" "FLI1"     "IRF2BP2"  "OXLD1"    "PAPOLG"   "SS18"    
##  [7] "ZNF821"   "ADAR"     "AFF1"     "ARHGAP4"  "DEK"      "DHX29"   
## [13] "DIS3"     "ETV6"     "IFIT2"    "IQSEC1"   "KIF2A"    "MLEC"    
## [19] "MLLT10"   "MLLT6"    "POGLUT1"  "PVT1"     "ROMO1"    "SECISBP2"
## [25] "SOCS2"    "ZNF593"

## [1] 19
##  [1] "AC008105.3" "AC145124.1" "ADK"        "DGKA"       "MMP28"     
##  [6] "NT5DC1"     "WARS2"      "AC020915.3" "AC022916.1" "APOL1"     
## [11] "BISPR"      "ECPAS"      "FRMD4B"     "HELB"       "ICE1"      
## [16] "IGLV3-25"   "MTRNR2L8"   "MX2"        "NCBP3"      "PRMT2"     
## [21] "RSAD2"      "SESN3"      "SETD5"      "SP140L"     "SPATA13"   
## [26] "TCAF2"      "TTTY15"     "UTP25"

## [1] 20
##  [1] "ARID4A"  "COG5"    "DPEP2"   "GATA3"   "HEATR5B" "HELQ"    "MTO1"   
##  [8] "MXD1"    "NABP1"   "PARP16"  "PRKCH"   "RASSF3"  "SIKE1"   "ST3GAL1"
## [15] "STX16"   "ZNF490"  "CCDC88C" "CHD6"    "FRY"     "FRYL"    "FUT11"  
## [22] "NBEAL2"  "SLMAP"   "TBX21"   "ZBTB8OS"

## [1] 21
##  [1] "CSRNP1"  "DAPP1"   "EFCAB2"  "IL6R"    "KANSL2"  "KDM6A"   "MYLIP"  
##  [8] "NR1D1"   "NR1D2"   "TBCK"    "TCTA"    "ASCL2"   "C12orf4" "CARD11" 
## [15] "CREBZF"  "KANSL1"  "KMT2B"   "KMT2C"   "KMT2D"   "NFE2L1"  "PHF20"  
## [22] "PHF20L1" "SCAF8"   "UBE3B"   "UTY"

## [1] 22
##  [1] "BTG1"    "BTG2"    "FBXL3"   "FHIT"    "INPP4B"  "KIF9"    "NR4A3"  
##  [8] "NSUN6"   "RGS10"   "SH3YL1"  "TECPR1"  "ACAP1"   "ANKAR"   "CCDC88B"
## [15] "CGGBP1"  "CYTIP"   "EFR3A"   "ISG20"   "KIF3B"   "KLF6"    "NARF"   
## [22] "P4HTM"   "PYCARD"  "RECK"    "TBC1D14" "TRAPPC8" "TSHZ2"

## [1] 23
##  [1] "BTN3A1"    "CD28"      "CD82"      "MZF1"      "PECAM1"    "PITPNC1"  
##  [7] "PLK3"      "PTPRCAP"   "TMEM245"   "TNFRSF25"  "YPEL5"     "APOBEC3G" 
## [13] "BTN3A2"    "CARD8-AS1" "CCL5"      "CCR4"      "CD2"       "CD58"     
## [19] "CST7"      "GAB3"      "GNLY"      "ITGAL"     "PLEK"      "PTPRC"    
## [25] "SMPD2"     "SPON2"     "TAOK3"

## [1] 24
##  [1] "IER3"    "KLF10"   "PLEKHM1" "AP3M2"   "C1orf21" "COL6A3"  "CRIP2"  
##  [8] "CRTC3"   "DDX3Y"   "EIF1AY"  "ETNK1"   "IL21R"   "KDM5D"   "LAIR2"  
## [15] "LPIN1"   "LPIN2"   "NLRC5"   "PIM1"    "PPP2R5B" "RNF157"  "RNPEPL1"
## [22] "RTKN2"   "SBNO2"   "SUSD6"   "TAF4B"   "TNFRSF4" "ZNF236"

## [1] 25
##  [1] "AC097376.2" "AL135791.1" "AL359220.1" "ARMH1"      "CERNA1"    
##  [6] "CHRM3-AS2"  "ERVK3-1"    "IPCEF1"     "JAML"       "LINC00623" 
## [11] "LINC01215"  "LINC01550"  "MATR3-1"    "MHENCR"     "MMP24OS"   
## [16] "NPIPB5"     "NSMCE3"     "PITPNA-AS1" "RETREG1"    "TRABD2A"   
## [21] "TRAV21"     "TRAV25"     "TRBV5-4"    "TRBV6-5"    "ZFP14"     
## [26] "ZNF506"     "ZNF91"      "PUS7L"

## [1] 26
##  [1] "ACADSB"    "C12orf45"  "CDKN2AIP"  "FBXO8"     "GSTM4"     "GTPBP10"  
##  [7] "GTPBP6"    "HIST1H2BC" "IP6K2"     "METAP1"    "NELFCD"    "PHLDA1"   
## [13] "ZNF7"      "C2orf68"   "CAMTA2"    "GUF1"      "HELZ2"     "IGHMBP2"  
## [19] "MTRF1L"    "PDE12"     "SUPV3L1"   "TRMT10C"   "ZNF483"    "ZNF708"

## [1] 27
##  [1] "C6orf62" "CAMK4"   "CCDC66"  "CCM2"    "CEP120"  "CEP95"   "CITED2" 
##  [8] "DPYD"    "EPS8"    "GADD45B" "HIVEP2"  "HOXB2"   "IER2"    "KLF12"  
## [15] "ODF2L"   "PIK3IP1" "PNISR"   "RCAN3"   "RCSD1"   "SLC44A1" "TESPA1" 
## [22] "TGIF1"   "ZFP36L1" "BLOC1S6" "IFI44L"  "VPS36"   "WDR7"

## [1] 28
##  [1] "ABCG1"       "AC025171.2"  "AC027644.3"  "AC084033.3"  "ARF4-AS1"   
##  [6] "ARRDC2"      "GOLGA8B"     "GPCPD1"      "JCHAIN"      "KCNQ1OT1"   
## [11] "LINC00649"   "LINC02265"   "LINC02273"   "MDS2"        "MFSD14C"    
## [16] "MUC20-OT1"   "MZF1-AS1"    "NAA16"       "NDUFV2-AS1"  "NOCT"       
## [21] "NPIPB11"     "RNASEH1-AS1" "ST7L"        "THAP9-AS1"   "TRAV8-6"    
## [26] "TRBV7-3"     "ZNF600"      "AREG"        "PKNOX1"

## [1] 29
##  [1] "AC009061.2" "ANKH"       "CCNI"       "COA1"       "COX10"     
##  [6] "CRLF3"      "DNASE1"     "ENOSF1"     "FCMR"       "FYB1"      
## [11] "IGKV1-5"    "LIMD2"      "LRRN3"      "NUDT4"      "ORC4"      
## [16] "PCNP"       "SLC8B1"     "SPIDR"      "STARD10"    "TMEM154"   
## [21] "TMEM71"     "TRBV6-2"    "TUBD1"      "TUBE1"      "YY1AP1"    
## [26] "ZFAS1"      "ZNF140"     "SLC23A2"    "TMEM175"

## [1] 30
##  [1] "ACSS1"    "AIF1"     "ATP5MG"   "C7orf31"  "DENND2D"  "DUSP1"   
##  [7] "FAM102A"  "HIST1H4C" "KLRB1"    "LTB"      "METTL21A" "NECAP2"  
## [13] "NOP53"    "RACK1"    "RASA2"    "RPL36A"   "RPS26"    "TIA1"    
## [19] "TOMM7"    "TSPYL1"   "TSPYL2"   "TSPYL4"   "ZFX"      "HSH2D"   
## [25] "MX1"      "NUP160"   "OAS1"

## [1] 31
##  [1] "ABCC10"      "ABHD2"       "ABHD3"       "AC116407.2"  "AC118549.1" 
##  [6] "ADTRP"       "ATAD2B"      "C20orf204"   "FAAH2"       "GPR132"     
## [11] "HACD3"       "HRH2"        "KANSL1-AS1"  "LRRC58"      "MFSD14A"    
## [16] "NBDY"        "NDUFC1"      "NRDC"        "OSM"         "PARP11"     
## [21] "PCSK1N"      "PUM3"        "SLF2"        "THUMPD3-AS1" "TMEM138"    
## [26] "TOMM70"      "TSPAN14"     "Z93930.2"    "ZFYVE28"

## [1] 32
##  [1] "AC004687.1" "AC004854.2" "AC016405.3" "AC020911.2" "AC023157.3"
##  [6] "AC025171.3" "AC083880.1" "AC091271.1" "AC103591.3" "AF213884.3"
## [11] "AL121944.1" "AL139246.5" "AL357060.1" "AL451085.1" "AL627171.1"
## [16] "AL645728.1" "ATP2B1-AS1" "BX284668.6" "C6orf99"    "HIPK1-AS1" 
## [21] "ID3"        "KLHL6"      "LINC01465"  "NPIPB4"     "NUP58"     
## [26] "OSER1-DT"   "SDR42E2"    "Z93241.1"   "SNHG9"

## [1] 34
##  [1] "ABTB1"    "CHURC1"   "CIRBP"    "EIF3G"    "EIF3K"    "EIF3M"   
##  [7] "EIF4A2"   "EPB41"    "KLHL24"   "LIMS1"    "MAP4K2"   "MARCKSL1"
## [13] "NMT2"     "NOSIP"    "POLL"     "SCRN2"    "SERTAD2"  "UXT"     
## [19] "WDR48"    "DDX60"    "PARVG"    "RSU1"     "TRIB2"    "USP46"

## [1] 35
##  [1] "CD52"     "COMMD6"   "COMMD9"   "CYB5D2"   "FCGRT"    "HLA-B"   
##  [7] "HLA-E"    "HLA-F"    "KIF20B"   "SCPEP1"   "SGSM3"    "TNFAIP8" 
## [13] "ZHX2"     "B2M"      "COMMD2"   "DIAPH2"   "EAPP"     "EMB"     
## [19] "G2E3"     "HLA-DRB5" "MR1"      "PRF1"     "SHOC2"    "ST6GAL1" 
## [25] "TAPBP"

## [1] 36
##  [1] "CCNL1"    "CENPK"    "CLK4"     "ITGB3BP"  "NKTR"     "PDCD7"   
##  [7] "PRPF38B"  "RSRP1"    "SMDT1"    "ZNF677"   "ZRSR2"    "CLASRP"  
## [13] "CWC25"    "ERICH1"   "IFI6"     "KMT2E"    "NKAP"     "PARP4"   
## [19] "PIP4K2B"  "SAMD9"    "SFSWAP"   "SLTM"     "SREK1IP1" "ZNF195"

## [1] 37
##  [1] "AKIRIN1"  "AKIRIN2"  "CD83"     "CLDND1"   "FAM8A1"   "MYADM"   
##  [7] "OSER1"    "ALOX5AP"  "ATXN7L3B" "BROX"     "CD320"    "CD7"     
## [13] "CDK2AP2"  "DENND4B"  "FBXO9"    "LY96"     "NT5C"     "PSMB9"   
## [19] "PSME2"    "RNF145"   "SDR39U1"  "SELL"     "SLC20A2"  "TIPARP"  
## [25] "UGCG"

## [1] 38
##  [1] "NSMAF"    "TBC1D10C" "APH1B"    "CISH"     "CITED4"   "CTBS"    
##  [7] "EHMT1"    "GABPB2"   "GMFB"     "ICOS"     "IFI35"    "KCNAB2"  
## [13] "KLF9"     "LTBP3"    "NADSYN1"  "NEK9"     "NME3"     "PLAC8"   
## [19] "PRDM2"    "PREP"     "REXO2"    "SLC9A8"   "STK10"    "STK17B"  
## [25] "TOB1"     "ZNF101"   "ZNF276"

## [1] 39
##  [1] "RBKS"       "UPF3A"      "AC016831.7" "AGAP2"      "APBB1IP"   
##  [6] "ARL4C"      "CARMIL2"    "CD55"       "CEMIP2"     "CRYBG1"    
## [11] "DDIT4"      "GPRIN3"     "GRK2"       "IFITM2"     "IRAK4"     
## [16] "MIAT"       "MT1X"       "NFKBIZ"     "NORAD"      "NSD3"      
## [21] "ODF3B"      "PHPT1"      "RAP1GAP2"   "RPS4Y1"     "SIGIRR"    
## [26] "SLC25A37"   "SMIM37"     "TENT5C"

## [1] 40
##  [1] "APOL6"    "BCL9L"    "CMIP"     "CROT"     "EIF2AK4"  "FAM53B"  
##  [7] "GIMAP4"   "GIMAP7"   "GZMM"     "IL32"     "KIAA1551" "KLHDC4"  
## [13] "LY6E"     "MCTP2"    "MT2A"     "NQO2"     "PDE4B"    "PEX11B"  
## [19] "PLA2G16"  "RCBTB2"   "RNMT"     "SEC14L1"  "SH3BP5"   "SYNE1"   
## [25] "SYTL1"    "TGFBR3"   "VPS13D"   "ZBP1"     "ZNF292"

for(n1 in names(goseq_res)){
  k = as.numeric(gsub("set_", "", n1))
  print(n1)
  print(gene_sets[[k]])
  print(goseq_res[[n1]])

}

## [1] "set_1"
##  [1] "CCNH"     "ERCC5"    "LAX1"     "POU2F2"   "SENP7"    "UTP6"    
##  [7] "ARHGAP10" "ARID5B"   "DTX3L"    "GBP1"     "GBP3"     "GBP5"    
## [13] "GON4L"    "IRF1"     "IRF9"     "MIER1"    "MYO1F"    "MYO1G"   
## [19] "PARP14"   "PARP9"    "RHOH"     "RNF19A"   "SAMD9L"   "SH3BP2"  
## [25] "TGS1"     "XAF1"    
## $go_bp
##                                     category over_represented_pvalue
## 486  cellular response to type ii interferon            8.785528e-07
## 4273          response to type ii interferon            2.225328e-06
## 4279                       response to virus            1.458046e-05
## 623             defense response to symbiont            1.817471e-05
##      under_represented_pvalue numDEInCat numInCat         FDR
## 486                 1.0000000          6       25 0.004202118
## 4273                0.9999999          6       30 0.005321873
## 4279                0.9999985          9      110 0.021732406
## 623                 0.9999984          8       81 0.021732406
## 
## $immune
##                                                                               category
## 4963 howard monocyte inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy up
## 4972   howard t cell inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy up
## 4961 howard dendritic cell inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 
## 4965 howard neutrophil inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy 
## 473                                                    gse14000 unstim vs 4h lps dc dn
## 4971 howard pbmc inact monov influenza a indonesia 05 2005 h5n1 age 19 39yo as03 adjuv
## 4082                                            gse42724 naive bcell vs plasmablast up
## 1353                                       gse18791 unstim vs newcatsle virus dc 6h dn
## 4959   howard b cell inact monov influenza a indonesia 05 2005 h5n1 age 18 49yo 1dy up
## 1343                                         gse18791 ctrl vs newcastle virus dc 8h dn
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 4963            9.865687e-09                1.0000000         10       64
## 4972            1.415117e-08                1.0000000          7       23
## 4961            1.726673e-08                1.0000000          9       54
## 4965            4.263786e-08                1.0000000         11      104
## 473             1.294206e-07                1.0000000          9       62
## 4971            1.660972e-07                1.0000000          9       67
## 4082            2.650341e-07                1.0000000          9       67
## 1353            6.234508e-07                1.0000000          9       67
## 4959            2.057931e-06                1.0000000          4        7
## 1343            2.828525e-06                0.9999998          8       61
##               FDR
## 4963 2.938797e-05
## 4972 2.938797e-05
## 4961 2.938797e-05
## 4965 5.442723e-05
## 473  1.321643e-04
## 4971 1.413487e-04
## 4082 1.933234e-04
## 1353 3.979175e-04
## 4959 1.167533e-03
## 1343 1.444245e-03
## 
## [1] "set_2"
##  [1] "CHD2"        "ADGRE5"      "ADGRG1"      "AKNA"        "CARD16"     
##  [6] "CCL4"        "CD300A"      "CTSW"        "FCRL6"       "FGFBP2"     
## [11] "GPR65"       "KIAA0040"    "MESD"        "MIR4435-2HG" "MYBL1"      
## [16] "NAA38"       "PAXX"        "RASAL3"      "S100A12"     "S1PR5"      
## [21] "SLFN12L"     "TRANK1"      "TRAV29DV5"   "TRBV6-1"     "TSPAN32"    
## [26] "TTC38"       "UBALD2"      "ZNF683"     
## $reactome
##                category over_represented_pvalue under_represented_pvalue
## 413 gpcr ligand binding            4.483661e-05                0.9999988
##     numDEInCat numInCat        FDR
## 413          4       24 0.05384877
## 
## $go_bp
##                                                                     category
## 45 adenylate cyclase activating g protein coupled receptor signaling pathway
##    over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 45             1.54217e-05                0.9999997          4       17
##           FDR
## 45 0.07376199
## 
## $immune
##                                                     category
## 4251 gse45739 unstim vs acd3 acd28 stim nras ko cd4 tcell dn
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 4251            1.385538e-05                0.9999992          6       41
##             FDR
## 4251 0.07074555
## 
## [1] "set_7"
##  [1] "CBR3"     "CHMP4A"   "CST3"     "DNAAF2"   "GGT7"     "SLC25A32"
##  [7] "TBPL1"    "USP3"     "B3GALT4"  "CCDC112"  "CTSC"     "DOCK11"  
## [13] "EFHD2"    "FKBP11"   "GNG2"     "GZMB"     "LPCAT4"   "LRRFIP1" 
## [19] "MATK"     "NKG7"     "PMVK"     "PREX1"    "PTGDR"    "SACS"    
## [25] "SH3BGRL3" "SMAP1"    "SRGN"    
## $immune
##                                                     category
## 3824 gse40274 ctrl vs lef1 transduced activated cd4 tcell up
## 2395                   gse26495 naive vs pd1low cd8 tcell dn
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 3824            2.550148e-06                0.9999999          6       31
## 2395            7.756712e-06                0.9999994          8       80
##             FDR
## 3824 0.01302106
## 2395 0.01980289
## 
## [1] "set_9"
##  [1] "CBLL1"    "CD38"     "CDC37L1"  "DSE"      "FCGR3A"   "GIMAP8"  
##  [7] "LCP2"     "SLC25A33" "SNX18"    "TRBC2"    "ZBTB25"   "C4orf48" 
## [13] "FAM129A"  "GNG5"     "GNPTAB"   "HLA-DPA1" "LAG3"     "NDUFA3"  
## [19] "NRROS"    "NUS1"     "OAS2"     "SLA"      "SPOCK2"   "SRP54"   
## [25] "TRAT1"    "UBR2"    
## $immune
##                                      category over_represented_pvalue
## 4511      gse6259 33d1 pos dc vs cd4 tcell dn            2.091002e-05
## 341  gse13306 treg vs tconv lamina propria up            2.777608e-05
##      under_represented_pvalue numDEInCat numInCat        FDR
## 4511                0.9999991          5       28 0.07091234
## 341                 0.9999988          5       30 0.07091234
## 
## [1] "set_10"
##  [1] "ARMCX5"   "C17orf49" "CXorf57"  "DBP"      "FOXO1"    "HIST1H3H"
##  [7] "NEK1"     "PEX6"     "PHYH"     "RNF113A"  "SBF2"     "YPEL2"   
## [13] "ZSCAN18"  "COLGALT1" "FNDC3B"   "GCA"      "GNPAT"    "KHNYN"   
## [19] "KIF21A"   "KIF21B"   "PEX26"    "PHF23"    "PLEKHA2"  "RAPGEF1" 
## [25] "TNFRSF18"
## $reactome
##                       category over_represented_pvalue under_represented_pvalue
## 712 peroxisomal protein import            7.521705e-06                0.9999999
##     numDEInCat numInCat         FDR
## 712          4        9 0.009033567
## 
## $immune
##                                         category over_represented_pvalue
## 1746 gse21927 balbc vs c57bl6 monocyte spleen up            4.928619e-06
##      under_represented_pvalue numDEInCat numInCat        FDR
## 1746                0.9999999          5       19 0.02516553
## 
## [1] "set_11"
##  [1] "ANAPC4"  "ATF4"    "EGR1"    "EIF1"    "EIF5"    "EPHB6"   "EPHX2"  
##  [8] "FOSB"    "JUNB"    "LYRM7"   "MALAT1"  "NDE1"    "NEU1"    "NUP54"  
## [15] "PLCD1"   "PNRC1"   "SAT1"    "SP3"     "STK19"   "TCF7"    "TOB2"   
## [22] "BHLHE40" "GPHN"    "MAF"     "SRFBP1"  "TRAC"   
## $immune
##                                                       category
## 2098                     gse23925 light zone vs naive bcell up
## 2093                      gse23925 dark zone vs naive bcell dn
## 796  gse16385 rosiglitazone ifng tnf vs il4 stim macrophage up
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 2098            7.625364e-06                0.9999995          7       59
## 2093            1.526653e-05                0.9999991          6       43
## 796             3.989776e-05                0.9999973          6       51
##             FDR
## 2098 0.03893511
## 2093 0.03897545
## 796  0.06790599
## 
## [1] "set_12"
##  [1] "AP002360.1" "ARHGAP15"   "C1GALT1"    "CD27"       "ERAP2"     
##  [6] "FCN1"       "GIMAP1"     "IGLV1-44"   "IGLV2-14"   "JPX"       
## [11] "KCNK6"      "KLF7"       "LEPROT"     "LRMP"       "PCMTD2"    
## [16] "PYROXD1"    "RAB37"      "SLC38A1"    "STK17A"     "TRBC1"     
## [21] "TTC39C"     "UCP2"       "XRRA1"      "ZNF84"      "ZNF862"    
## [26] "GZMA"       "IFI44"      "KLRG1"     
## $reactome
##                             category over_represented_pvalue
## 187 creation of c4 and c2 activators            1.511544e-05
## 460 initial triggering of complement            4.594495e-05
## 171               complement cascade            9.527436e-05
##     under_represented_pvalue numDEInCat numInCat        FDR
## 187                0.9999999          3        6 0.01815364
## 460                0.9999995          3        8 0.02758994
## 171                0.9999987          3       10 0.03814150
## 
## [1] "set_21"
##  [1] "CSRNP1"  "DAPP1"   "EFCAB2"  "IL6R"    "KANSL2"  "KDM6A"   "MYLIP"  
##  [8] "NR1D1"   "NR1D2"   "TBCK"    "TCTA"    "ASCL2"   "C12orf4" "CARD11" 
## [15] "CREBZF"  "KANSL1"  "KMT2B"   "KMT2C"   "KMT2D"   "NFE2L1"  "PHF20"  
## [22] "PHF20L1" "SCAF8"   "UBE3B"   "UTY"    
## $reactome
##                                                     category
## 352 formation of wdr5 containing histone modifying complexes
## 295                 epigenetic regulation of gene expression
## 153                              chromatin modifying enzymes
##     over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 352            0.000000e+00                        1          8       16
## 295            3.820039e-09                        1          8       38
## 153            2.349559e-07                        1          8       61
##              FDR
## 352 0.000000e+00
## 295 2.293933e-06
## 153 9.406067e-05
## 
## $go_bp
##                                                               category
## 1115                                              histone modification
## 1112                                         histone h3 k4 methylation
## 1114                                               histone methylation
## 2369                                       peptidyl lysine methylation
## 2689                        positive regulation of histone methylation
## 3476 regulation of dosage compensation by inactivation of x chromosome
## 3580                           regulation of histone h3 k4 methylation
## 1499                                                       methylation
## 3147                                               protein methylation
## 3581                                 regulation of histone methylation
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 1115            8.178156e-08                1.0000000          7       29
## 1112            3.349995e-06                1.0000000          4        8
## 1114            6.901604e-06                0.9999999          4       10
## 2369            1.702087e-05                0.9999997          4       12
## 2689            2.510890e-05                0.9999998          3        5
## 3476            2.510890e-05                0.9999998          3        5
## 3580            2.510890e-05                0.9999998          3        5
## 1499            3.991079e-05                0.9999973          6       44
## 3147            4.107974e-05                0.9999989          4       15
## 3581            6.230887e-05                0.9999993          3        7
##               FDR
## 1115 0.0003911612
## 1112 0.0080115137
## 1114 0.0110034567
## 2369 0.0171565503
## 2689 0.0171565503
## 3476 0.0171565503
## 3580 0.0171565503
## 1499 0.0218316008
## 3147 0.0218316008
## 3581 0.0298023317
## 
## [1] "set_23"
##  [1] "BTN3A1"    "CD28"      "CD82"      "MZF1"      "PECAM1"    "PITPNC1"  
##  [7] "PLK3"      "PTPRCAP"   "TMEM245"   "TNFRSF25"  "YPEL5"     "APOBEC3G" 
## [13] "BTN3A2"    "CARD8-AS1" "CCL5"      "CCR4"      "CD2"       "CD58"     
## [19] "CST7"      "GAB3"      "GNLY"      "ITGAL"     "PLEK"      "PTPRC"    
## [25] "SMPD2"     "SPON2"     "TAOK3"    
## $immune
##                                                                               category
## 5048 patel skin of body zostavax age 70 93yo vzv challenged post vaccination vs unchal
## 3015                                     gse32986 unstim vs curdlan lowdose stim dc dn
## 4253                                gse45739 unstim vs acd3 acd28 stim wt cd4 tcell dn
## 1384                                          gse19198 6h vs 24h il21 treated tcell up
## 2617                                                  gse27786 lin neg vs cd8 tcell dn
## 2395                                             gse26495 naive vs pd1low cd8 tcell dn
## 2887                                       gse3039 nkt cell vs alphaalpha cd8 tcell dn
## 30              fuller pbmc f tularensis vaccine lvs age 22 54yo 18hr to 48hr early dn
## 140                                          gse11057 eff mem vs cent mem cd4 tcell up
## 4251                           gse45739 unstim vs acd3 acd28 stim nras ko cd4 tcell dn
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 5048            3.450920e-06                1.0000000          4        9
## 3015            6.124880e-06                0.9999997          6       37
## 4253            1.005958e-05                0.9999993          7       61
## 1384            1.976838e-05                0.9999992          5       27
## 2617            3.124459e-05                0.9999980          6       49
## 2395            6.071575e-05                0.9999943          7       80
## 2887            8.742795e-05                0.9999930          6       58
## 30              1.144337e-04                0.9999957          4       20
## 140             1.254127e-04                0.9999921          5       39
## 4251            1.692857e-04                0.9999886          5       41
##             FDR
## 5048 0.01563682
## 3015 0.01563682
## 4253 0.01712141
## 1384 0.02523433
## 2617 0.03190697
## 2395 0.05166911
## 2887 0.06377245
## 30   0.07115081
## 140  0.07115081
## 4251 0.08643730
## 
## [1] "set_24"
##  [1] "IER3"    "KLF10"   "PLEKHM1" "AP3M2"   "C1orf21" "COL6A3"  "CRIP2"  
##  [8] "CRTC3"   "DDX3Y"   "EIF1AY"  "ETNK1"   "IL21R"   "KDM5D"   "LAIR2"  
## [15] "LPIN1"   "LPIN2"   "NLRC5"   "PIM1"    "PPP2R5B" "RNF157"  "RNPEPL1"
## [22] "RTKN2"   "SBNO2"   "SUSD6"   "TAF4B"   "TNFRSF4" "ZNF236" 
## $reactome
##                       category over_represented_pvalue under_represented_pvalue
## 1073           synthesis of pe            1.159467e-06                        1
## 1170 triglyceride biosynthesis            1.192278e-04                        1
##      numDEInCat numInCat         FDR
## 1073          3        3 0.001392519
## 1170          2        2 0.071596271
## 
## [1] "set_34"
##  [1] "ABTB1"    "CHURC1"   "CIRBP"    "EIF3G"    "EIF3K"    "EIF3M"   
##  [7] "EIF4A2"   "EPB41"    "KLHL24"   "LIMS1"    "MAP4K2"   "MARCKSL1"
## [13] "NMT2"     "NOSIP"    "POLL"     "SCRN2"    "SERTAD2"  "UXT"     
## [19] "WDR48"    "DDX60"    "PARVG"    "RSU1"     "TRIB2"    "USP46"   
## $go_bp
##                                 category over_represented_pvalue
## 611 cytoplasmic translational initiation            1.350949e-05
##     under_represented_pvalue numDEInCat numInCat        FDR
## 611                0.9999997          4       12 0.06461587
## 
## [1] "set_35"
##  [1] "CD52"     "COMMD6"   "COMMD9"   "CYB5D2"   "FCGRT"    "HLA-B"   
##  [7] "HLA-E"    "HLA-F"    "KIF20B"   "SCPEP1"   "SGSM3"    "TNFAIP8" 
## [13] "ZHX2"     "B2M"      "COMMD2"   "DIAPH2"   "EAPP"     "EMB"     
## [19] "G2E3"     "HLA-DRB5" "MR1"      "PRF1"     "SHOC2"    "ST6GAL1" 
## [25] "TAPBP"   
## $reactome
##                                                                     category
## 56  antigen presentation folding assembly and peptide loading of class i mhc
## 288                                               endosomal vacuolar pathway
## 57                                     antigen processing cross presentation
## 477                                               interferon gamma signaling
## 206                                                       dap12 interactions
## 932      sars cov 2 activates modulates innate and adaptive immune responses
## 451 immunoregulatory interactions between a lymphoid and a non lymphoid cell
## 160                     class i mhc mediated antigen processing presentation
##     over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 56             4.446686e-08                1.0000000          5       10
## 288            6.429708e-07                1.0000000          4        7
## 57             2.537915e-06                0.9999999          5       20
## 477            4.744798e-05                0.9999978          5       35
## 206            9.600271e-05                0.9999987          3        8
## 932            2.017524e-04                0.9999916          4       25
## 451            5.427153e-04                0.9999699          4       32
## 160            6.093877e-04                0.9999494          5       59
##              FDR
## 56  0.0000534047
## 288 0.0003861040
## 57  0.0010160122
## 477 0.0142462569
## 206 0.0230598509
## 932 0.0403841127
## 451 0.0914843242
## 160 0.0914843242
## 
## $go_bp
##                                                                     category
## 129   antigen processing and presentation of peptide antigen via mhc class i
## 128                   antigen processing and presentation of peptide antigen
## 4560                                            t cell mediated cytotoxicity
## 122                                      antigen processing and presentation
## 2559                                     positive regulation of cell killing
## 2967                     positive regulation of t cell mediated cytotoxicity
## 4019                              regulation of t cell mediated cytotoxicity
## 124        antigen processing and presentation of endogenous peptide antigen
## 130  antigen processing and presentation of peptide antigen via mhc class ib
## 132                     antigen processing and presentation via mhc class ib
##      over_represented_pvalue under_represented_pvalue numDEInCat numInCat
## 129             4.488655e-09                        1          6       13
## 128             5.844894e-09                        1          7       23
## 4560            7.789304e-09                        1          6       14
## 122             1.531719e-08                        1          7       26
## 2559            2.043029e-08                        1          6       16
## 2967            6.446195e-08                        1          5       10
## 4019            1.171559e-07                        1          5       11
## 124             1.171559e-07                        1          5       11
## 130             1.204240e-07                        1          4        5
## 132             1.204240e-07                        1          4        5
##               FDR
## 129  1.241875e-05
## 128  1.241875e-05
## 4560 1.241875e-05
## 122  1.831553e-05
## 2559 1.954362e-05
## 2967 5.138692e-05
## 4019 5.759878e-05
## 124  5.759878e-05
## 130  5.759878e-05
## 132  5.759878e-05
## 
## [1] "set_36"
##  [1] "CCNL1"    "CENPK"    "CLK4"     "ITGB3BP"  "NKTR"     "PDCD7"   
##  [7] "PRPF38B"  "RSRP1"    "SMDT1"    "ZNF677"   "ZRSR2"    "CLASRP"  
## [13] "CWC25"    "ERICH1"   "IFI6"     "KMT2E"    "NKAP"     "PARP4"   
## [19] "PIP4K2B"  "SAMD9"    "SFSWAP"   "SLTM"     "SREK1IP1" "ZNF195"  
## $go_bp
##          category over_represented_pvalue under_represented_pvalue numDEInCat
## 4338 rna splicing            3.274858e-08                        1         10
##      numInCat          FDR
## 4338       89 0.0001566365
## 
## [1] "set_39"
##  [1] "RBKS"       "UPF3A"      "AC016831.7" "AGAP2"      "APBB1IP"   
##  [6] "ARL4C"      "CARMIL2"    "CD55"       "CEMIP2"     "CRYBG1"    
## [11] "DDIT4"      "GPRIN3"     "GRK2"       "IFITM2"     "IRAK4"     
## [16] "MIAT"       "MT1X"       "NFKBIZ"     "NORAD"      "NSD3"      
## [21] "ODF3B"      "PHPT1"      "RAP1GAP2"   "RPS4Y1"     "SIGIRR"    
## [26] "SLC25A37"   "SMIM37"     "TENT5C"    
## $immune
##                            category over_represented_pvalue
## 504 gse14308 th2 vs natural treg up            1.801347e-05
##     under_represented_pvalue numDEInCat numInCat        FDR
## 504                0.9999993          5       24 0.09197677

saveRDS(goseq_res, sprintf("output/gene_set_enrichments_%s.RDS", 
                           file_tag))

Session information

gc()

##            used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
## Ncells  8958487 478.5   16391124 875.4         NA 16391124 875.4
## Vcells 19174998 146.3   56237081 429.1      65536 77218972 589.2

sessionInfo()

## R version 4.2.3 (2023-03-15)
## Platform: aarch64-apple-darwin20 (64-bit)
## Running under: macOS Ventura 13.4.1
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/lib/libRlapack.dylib
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
## [1] stats4    stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
##  [1] TxDb.Hsapiens.UCSC.hg38.knownGene_3.16.0
##  [2] GenomicFeatures_1.50.4                  
##  [3] GenomicRanges_1.50.2                    
##  [4] GenomeInfoDb_1.34.9                     
##  [5] org.Hs.eg.db_3.16.0                     
##  [6] AnnotationDbi_1.60.2                    
##  [7] IRanges_2.32.0                          
##  [8] S4Vectors_0.36.2                        
##  [9] Biobase_2.58.0                          
## [10] BiocGenerics_0.44.0                     
## [11] goseq_1.50.0                            
## [12] geneLenDataBase_1.34.0                  
## [13] BiasedUrn_2.0.10                        
## [14] fgsea_1.24.0                            
## [15] biomaRt_2.54.1                          
## [16] limma_3.54.2                            
## [17] tidyr_1.3.0                             
## [18] ggpubr_0.6.0                            
## [19] ggplot2_3.4.2                           
## [20] data.table_1.14.8                       
## 
## loaded via a namespace (and not attached):
##  [1] nlme_3.1-162                matrixStats_1.0.0          
##  [3] bitops_1.0-7                bit64_4.0.5                
##  [5] filelock_1.0.2              progress_1.2.2             
##  [7] httr_1.4.6                  tools_4.2.3                
##  [9] backports_1.4.1             bslib_0.4.2                
## [11] utf8_1.2.3                  R6_2.5.1                   
## [13] mgcv_1.8-42                 DBI_1.1.3                  
## [15] colorspace_2.1-0            withr_2.5.0                
## [17] tidyselect_1.2.0            prettyunits_1.1.1          
## [19] bit_4.0.5                   curl_5.0.1                 
## [21] compiler_4.2.3              cli_3.6.1                  
## [23] xml2_1.3.4                  DelayedArray_0.24.0        
## [25] rtracklayer_1.58.0          sass_0.4.5                 
## [27] scales_1.2.1                rappdirs_0.3.3             
## [29] Rsamtools_2.14.0            stringr_1.5.0              
## [31] digest_0.6.31               rmarkdown_2.21             
## [33] XVector_0.38.0              pkgconfig_2.0.3            
## [35] htmltools_0.5.5             MatrixGenerics_1.10.0      
## [37] dbplyr_2.3.2                fastmap_1.1.1              
## [39] rlang_1.1.0                 rstudioapi_0.14            
## [41] RSQLite_2.3.1               BiocIO_1.8.0               
## [43] jquerylib_0.1.4             generics_0.1.3             
## [45] jsonlite_1.8.4              BiocParallel_1.32.6        
## [47] dplyr_1.1.2                 car_3.1-2                  
## [49] RCurl_1.98-1.12             magrittr_2.0.3             
## [51] GO.db_3.16.0                GenomeInfoDbData_1.2.9     
## [53] Matrix_1.6-4                Rcpp_1.0.10                
## [55] munsell_0.5.0               fansi_1.0.4                
## [57] abind_1.4-5                 lifecycle_1.0.3            
## [59] stringi_1.7.12              yaml_2.3.7                 
## [61] carData_3.0-5               SummarizedExperiment_1.28.0
## [63] zlibbioc_1.44.0             BiocFileCache_2.6.1        
## [65] grid_4.2.3                  blob_1.2.4                 
## [67] parallel_4.2.3              crayon_1.5.2               
## [69] lattice_0.20-45             splines_4.2.3              
## [71] Biostrings_2.66.0           cowplot_1.1.1              
## [73] hms_1.1.3                   KEGGREST_1.38.0            
## [75] knitr_1.44                  pillar_1.9.0               
## [77] rjson_0.2.21                ggsignif_0.6.4             
## [79] codetools_0.2-19            fastmatch_1.1-3            
## [81] XML_3.99-0.14               glue_1.6.2                 
## [83] evaluate_0.20               png_0.1-8                  
## [85] vctrs_0.6.2                 gtable_0.3.3               
## [87] purrr_1.0.1                 cachem_1.0.7               
## [89] xfun_0.39                   broom_1.0.4                
## [91] restfulr_0.0.15             rstatix_0.7.2              
## [93] tibble_3.2.1                GenomicAlignments_1.34.1   
## [95] memoise_2.0.1